© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27390
    Prev
    Next
    INDEX
    Explanations

    implicated in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĤį
    -0.08
    ihad
    -0.08
    ç«ĭå¿Ĺ
    -0.08
    åĤ¨å¤ĩ
    -0.08
    大ä¼Ĺ
    -0.08
    åİĤ
    -0.08
    å¿ĥæĦı
    -0.07
    poi
    -0.07
    ä¹ĭåīį
    -0.07
    çħ§äº®
    -0.07
    POSITIVE LOGITS
    åľ¨åĨħçļĦ
    0.21
    à¹ĥà¸Ļà¸ģาร
    0.14
     in
    0.13
     ÙģÙī
    0.12
     ÙģÙĬ
    0.11
    äºİ
    0.11
     ÙģÙĬÙĩ
    0.11
    åľ¨äºİ
    0.10
    ÙģÙĬ
    0.10
    åľ¨æĦı
    0.10
    Activations Density 0.168%

    No Known Activations